Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    distance from

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     состоится
    0.97
    ni
    0.91
     lindas
    0.88
     नामित
    0.86
     лучших
    0.85
    s
    0.84
    sa
    0.82
    ulfanyl
    0.82
    stion
    0.82
    mi
    0.81
    POSITIVE LOGITS
    ו
    0.70
     juggle
    0.68
     перио
    0.67
     doba
    0.66
    عت
    0.64
     period
    0.64
    Checks
    0.64
    ਿੱ
    0.63
     khăn
    0.63
    وغ
    0.63
    Act Density 0.003%

    No Known Activations